Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    633
    -0.07
    ací
    -0.06
     ENUM
    -0.06
     FAG
    -0.06
    .vel
    -0.06
    放在
    -0.06
    >To
    -0.06
    OPTARG
    -0.06
     Slam
    -0.06
    .YEAR
    -0.06
    POSITIVE LOGITS
    ERN
    0.08
    igar
    0.07
     область
    0.07
    查看
    0.06
    Michael
    0.06
    ��作
    0.06
    χε
    0.06
    ?>"
    0.06
    检测
    0.06
    ###↵
    0.06
    Act Density 0.003%

    No Known Activations